Tensorflow argmax沿多个维度

Question

我是tensorflow的新手，我正在尝试得到张量中最大值的索引。代码如下：

def select(input_layer):

    shape = input_layer.get_shape().as_list()

    rel = tf.nn.relu(input_layer)
    print (rel)
    redu = tf.reduce_sum(rel,3)
    print (redu)

    location2 = tf.argmax(redu, 1)
    print (location2)

sess = tf.InteractiveSession()
I = tf.random_uniform([32, 3, 3, 5], minval = -541, maxval = 23, dtype = tf.float32)
matI, matO = sess.run([I, select(I, 3)])
print(matI, matO)

下面是输出：

Tensor("Relu:0", shape=(32, 3, 3, 5), dtype=float32)
Tensor("Sum:0", shape=(32, 3, 3), dtype=float32)
Tensor("ArgMax:0", shape=(32, 3), dtype=int64)
...

由于在argmax函数中使用了dimension=1，所以Tensor("ArgMax:0") = (32,3)的形状。有没有办法在应用argmax之前不执行reshape就获得argmax输出张量大小= (32,)

Answer 1

有问题的是，你不想要一个大小为(32,)的输出，因为当你沿着几个方向进行argmax时，你通常希望得到所有减少的维度的最大值的坐标。在您的示例中，您可能希望输出大小为(32,2)。

你可以像这样做一个二维argmax：

import numpy as np
import tensorflow as tf

x = np.zeros((10,9,8))
# pick a random position for each batch image that we set to 1
pos = np.stack([np.random.randint(9,size=10), np.random.randint(8,size=10)])

posext = np.concatenate([np.expand_dims([i for i in range(10)], axis=0), pos])
x[tuple(posext)] = 1

a = tf.argmax(tf.reshape(x, [10, -1]), axis=1)
pos2 = tf.stack([a // 8, tf.mod(a, 8)]) # recovered positions, one per batch image

sess = tf.InteractiveSession()
# check that the recovered positions are as expected
assert (pos == pos2.eval()).all(), "it did not work"